Search Results for author:
Found 7 papers, 0 papers with code
Improved Vocal Effort Transfer Vector Estimation for Vocal Effort-Robust Speaker Verification
Despite the maturity of modern speaker verification technology, its performance still significantly degrades when facing non-neutrally-phonated (e. g., shouted and whispered) speech.
Class Token and Knowledge Distillation for Multi-head Self-Attention Speaker Verification Systems
This paper explores three novel approaches to improve the performance of speaker verification (SV) systems based on deep neural networks (DNN) using Multi-head Self-Attention (MSA) mechanisms and memory layers.
Generalizing AUC Optimization to Multiclass Classification for Audio Segmentation With Limited Training Data
Area under the ROC curve (AUC) optimisation techniques developed for neural networks have recently demonstrated their capabilities in different audio and speech related tasks.
Shouted Speech Compensation for Speaker Verification Robust to Vocal Effort Conditions
These compensation techniques are borrowed from the area of robustness for automatic speech recognition and, in this work, we apply them to compensate the mismatch between shouted and normal conditions in speaker verification.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Optimization of the Area Under the ROC Curve using Neural Network Supervectors for Text-Dependent Speaker Verification
This paper explores two techniques to improve the performance of text-dependent speaker verification systems based on deep neural networks.
Tied Hidden Factors in Neural Networks for End-to-End Speaker Recognition
As in Joint Factor Analysis, the model uses tied hidden variables to model speaker and session variability and a MAP adaptation of some of the parameters of the model.
Differentiable Supervector Extraction for Encoding Speaker and Phrase Information in Text Dependent Speaker Verification
Moreover, we can apply a convolutional neural network as front-end, and thanks to the alignment process being differentiable, we can train the whole network to produce a supervector for each utterance which will be discriminative with respect to the speaker and the phrase simultaneously.
